Affiliations: [a] Department of Computer Science and Engineering, DAV University, Jalandhar, India
| [b] Department of Computer Science, Guru Nanak Dev University, Amritsar, India
Correspondence:
[*]
Corresponding author. Harpreet Singh, Assistant Professor, Department of Computer Science and Engineering, DAV University, Jalandhar-144012, India. Tel.: +91 9815735530; E-mail: harpreet99.nitj@gmail.com.
Abstract: As the size of websites continues to grow, current research focuses on the development of intelligent websites which facilitate the browsing by providing a navigation aid to the website users. Web page recommendation systems provide suggestions to the website users about the webpages that may be of concern to them by evaluating the collective navigation behavior of previous website users. The main motive of this study was to explore the utilization of partially ordered sequential rules (POSR) in making future predictions for website users. Sequential rules provide the association between the events that occur in a particular sequence. In this paper, two sequential rule mining algorithms, namely TRuleGrowth and CMRules have been separately used to generate sequential rules. Then the sequential rules were used to make predictions about the future interests of the users regarding webpages. The experimental results on a real life dataset have revealed that the rules generated by TRuleGrowth algorithm were able to make predictions with higher accuracy than those generated by CMRules algorithm.
Keywords: Sequential rule mining, partially ordered sequential rules, recommendation system
